# Single Image Object Counting and Localizing using Active-Learning

arXiv: https://arxiv.org/abs/2111.08383 · HTML: https://mlsanity.com/paper/2111.08383/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 12 of 12)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Video-to-Video Synthesis](https://mlsanity.com/paper/1808.06601/) (2018)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Drone-based Object Counting by Spatially Regularized Regional Proposal Network](https://mlsanity.com/paper/1707.05972/) (2017)
- [Class-Agnostic Counting](https://mlsanity.com/paper/1811.00472/) (2018)
- [Count-ception: Counting by Fully Convolutional Redundant Counting](https://mlsanity.com/paper/1703.08710/) (2017)
- [Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking](https://mlsanity.com/paper/1705.10118/) (2017)
- [Learning to count with deep object features](https://mlsanity.com/paper/1505.08082/) (2015)
- [Detecting Repeating Objects using Patch Correlation Analysis](https://mlsanity.com/paper/1904.05629/) (2019)

## Abstract (arXiv)

The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance recordings analysis. The use of supervised Convoutional Neural Networks (CNNs) achieves accurate object detection when trained over large class-specific datasets. The labeling effort in this approach does not pay-off when the counting is required over few images of a unique object class. We present a new method for counting and localizing repeating objects in single-image scenarios, assuming no pre-trained classifier is available. Our method trains a CNN over a small set of labels carefully collected from the input image in few active-learning iterations. At each iteration, the latent space of the network is analyzed to extract a minimal number of user-queries that strives to both sample the in-class manifold as thoroughly as possible as well as avoid redundant labels. Compared with existing user-assisted counting methods, our active-learning iterations achieve state-of-the-art performance in terms of counting and localizing accuracy, number of user mouse clicks, and running-time. This evaluation was performed through a large user study over a wide range of image classes with diverse conditions of illumination and occlusions.